Abstract
Recent works on learned image compression (LIC) based on convolutional neural networks (CNNs) have achieved great improvement with superior rate-distortion performance. However, the robustness of LIC has received little investigation. In this paper, we proposes a complex-valued learned image compression model based on complex-valued convolutional neural networks (CVCNNs) to enhance its robustness. Firstly, we design a complex-valued neural image compression framework, which realizes compression with complex-valued feature maps. Secondly, we build a module named modSigmoid to implement a complex-valued nonlinear transform and a split-complex entropy model to compress complex-valued latent. The experiment results show that the proposed model performs comparable compression performance with a large parameter drop. Moreover, we adopt the adversarial attack method to examine robustness, and the proposed model shows better robustness to adversarial input compared with its real-valued counterpart.
C. Luo and Y. Bao—These authors contributed to the work equally and should be regarded as co-first authors.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ballé, J., Laparra, V., Simoncelli, E.P.: End-to-end optimized image compression. arXiv preprint arXiv:1611.01704 (2016)
Ballé, J., Minnen, D., Singh, S., Hwang, S.J., Johnston, N.: Variational image compression with a scale hyperprior. arXiv preprint arXiv:1802.01436 (2018)
Bégaint, J., Racapé, F., Feltman, S., Pushparaja, A.: Compressai: a pytorch library and evaluation platform for end-to-end compression research. arXiv preprint arXiv:2011.03029 (2020)
Bellard, F.: BPG image format (2014). 1, 2 (2016)
Chen, T., Ma, Z.: Towards robust neural image compression: Adversarial attack and model finetuning. arXiv preprint arXiv:2112.08691 (2021)
Cheng, Z., Sun, H., Takeuchi, M., Katto, J.: Learned image compression with discretized gaussian mixture likelihoods and attention modules. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7939–7948 (2020)
Chiheb, T., Bilaniuk, O., Serdyuk, D., et al.: Deep complex networks. In: International Conference on Learning Representations (2017). https://openreview.net/forum
Danihelka, I., Wayne, G., Uria, B., Kalchbrenner, N., Graves, A.: Associative long short-term memory. In: International Conference on Machine Learning, pp. 1986–1994. PMLR (2016)
Dow, B.M.: Functional classes of cells and their laminar distribution in monkey visual cortex. J. Neurophysiol. 37(5), 927–946 (1974)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)
Li, B., Xin, Y., Li, C., Bao, Y., Meng, F., Liang, Y.: Adderic: towards low computation cost image compression. In: ICASSP 2022–2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2030–2034 (2022). https://doi.org/10.1109/ICASSP43922.2022.9747652
Liu, K., Wu, D., Wang, Y., Feng, D., Tan, B., Garg, S.: Denial-of-service attacks on learned image compression. arXiv preprint arXiv:2205.13253 (2022)
Minnen, D., Ballé, J., Toderici, G.D.: Joint autoregressive and hierarchical priors for learned image compression. Adv. Neural Inf. Process. Syst. 31 (2018)
Nitta, T.: The computational power of complex-valued neuron. In: Kaynak, O., Alpaydin, E., Oja, E., Xu, L. (eds.) Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003, pp. 993–1000. Springer, Heidelberg (2003). https://doi.org/10.1007/3-540-44989-2_118
Quan, Y., Chen, Y., Shao, Y., Teng, H., Xu, Y., Ji, H.: Image denoising using complex-valued deep CNN. Pattern Recogn. 111, 107639 (2021)
Singhal, U., Xing, Y., Yu, S.X.: Co-domain symmetry for complex-valued deep learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 681–690 (2022)
Szegedy, C., et al.: Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013)
Yin, S., Li, C., Bao, Y., Liang, Y., Meng, F., Liu, W.: Universal efficient variable-rate neural image compression. In: ICASSP 2022–2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2025–2029 (2022). https://doi.org/10.1109/ICASSP43922.2022.9747854
Yu, S.: Angular embedding: a robust quadratic criterion. IEEE Trans. Pattern Anal. Mach. Intell. 34(1), 158–173 (2011)
Acknowledgment
This research was supported by the National Natural Science Foundation of China (Grant No. 62031013), the Guangdong Province Key Construction Discipline Scientific Research Capacity Improvement Project (Grant No. 2022ZDJS117), and the project of Peng Cheng Laboratory. The computing resources of Pengcheng Cloudbrain are used in this research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Luo, C., Bao, Y., Tan, W., Li, C., Meng, F., Liang, Y. (2024). A Complex-Valued Neural Network Based Robust Image Compression. In: Liu, Q., et al. Pattern Recognition and Computer Vision. PRCV 2023. Lecture Notes in Computer Science, vol 14434. Springer, Singapore. https://doi.org/10.1007/978-981-99-8549-4_5
Download citation
DOI: https://doi.org/10.1007/978-981-99-8549-4_5
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8548-7
Online ISBN: 978-981-99-8549-4
eBook Packages: Computer ScienceComputer Science (R0)